Analysis of the algorithm: From kernels to backup genes.

Kernelization section

The algorithm transformed the semantic similarity matrix to make it compatible with a kernel. Once this was done for each network and kernel type, it was integrated by kernel type. Below there is a general analysis of the properties of each matrix in the different phases of the process.

Annotations properties

Table 1. Annotation files descriptors

Net Kernel Elements Min Max Average Standard_Deviation
cellular_component ct 2 0.483516 0.736264 0.60989 0.12637400000000001
cellular_component rf 2 0.483516 0.736264 0.60989 0.12637400000000001
biological_process ct 2 0.130952 0.869048 0.5 0.36904800000000004
biological_process rf 2 0.130952 0.880952 0.505952 0.375
molecular_function rf 2 0.146067 0.393258 0.2696625 0.1235955
molecular_function ct 2 0.089888 0.393258 0.24157299999999998 0.15168500000000001
phenotype rf 4 0.029703 0.811881 0.30693075 0.3049278829054298
phenotype ct 4 0.029703 0.930693 0.33663375 0.35443602095679766

Matrix properties

Table 2. Similarity matrixes

Integration Kernel Elements Min Max Average Standard_Deviation
mean rf 2 0.04 0.34 0.19 0.15000000000000002
mean ct 2 0.055 0.935 0.49500000000000005 0.44

Weight values